thebajajra commited on
Commit
29bacbc
·
verified ·
1 Parent(s): eb117cf

Upload FP8 quantized model

Browse files
Files changed (1) hide show
  1. config.json +2 -6
config.json CHANGED
@@ -60,11 +60,9 @@
60
  "num_bits": 8,
61
  "observer": "minmax",
62
  "observer_kwargs": {},
63
- "scale_dtype": null,
64
  "strategy": "tensor",
65
  "symmetric": true,
66
- "type": "float",
67
- "zp_dtype": null
68
  },
69
  "output_activations": null,
70
  "targets": [
@@ -78,11 +76,9 @@
78
  "num_bits": 8,
79
  "observer": "minmax",
80
  "observer_kwargs": {},
81
- "scale_dtype": null,
82
  "strategy": "tensor",
83
  "symmetric": true,
84
- "type": "float",
85
- "zp_dtype": null
86
  }
87
  }
88
  },
 
60
  "num_bits": 8,
61
  "observer": "minmax",
62
  "observer_kwargs": {},
 
63
  "strategy": "tensor",
64
  "symmetric": true,
65
+ "type": "float"
 
66
  },
67
  "output_activations": null,
68
  "targets": [
 
76
  "num_bits": 8,
77
  "observer": "minmax",
78
  "observer_kwargs": {},
 
79
  "strategy": "tensor",
80
  "symmetric": true,
81
+ "type": "float"
 
82
  }
83
  }
84
  },